Title :
The road tunnel fire detection of multi-parameters based on BP neural network
Author_Institution :
Basic Courses Teaching Dept., Armed Police Acad., Langfang, China
Abstract :
The temperature, the smoke density and the density of CO are selected as the main parameters of road tunnel fire detection, analyzing the environment and the characteristics of road tunnel fire. Based on BP neural network, the mathematical model is set up. Studying the algorithm of BP neural network, the model can identify road tunnel fire. The simulation result of road tunnel fire shows that the correct recognition probability is high. The false-alarm probability can be decreased. The suitability of this system to environmental variation can be obviously improved. The study and application of this method has a great theoretical and practical value for early prediction of road tunnel fires.
Keywords :
backpropagation; fires; neural nets; roads; structural engineering computing; tunnels; BP neural network; false-alarm probability; mathematical model; recognition probability; road tunnel fire detection; smoke density; Fires; Gas detectors; Multi-layer neural network; Neural networks; Road accidents; Robotics and automation; Smoke detectors; Space heating; Temperature sensors; Ventilation;
Conference_Titel :
Informatics in Control, Automation and Robotics (CAR), 2010 2nd International Asia Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-5192-0
Electronic_ISBN :
1948-3414
DOI :
10.1109/CAR.2010.5456677
